mlsanityData to 7 Oct 2026

Stable Virtual Camera: Generative View Synthesis with Diffusion Models

arXiv 2503.14489 ↗First posted 18 Mar 2025cs.CVcited by 179

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

We present Stable Virtual Camera (Seva), a generalist diffusion model that creates novel views of a scene, given any number of input views and target cameras. Existing works struggle to generate either large viewpoint changes or temporally smooth samples, while relying on specific task configurations. Our approach overcomes these limitations through simple model design, optimized training recipe, and flexible sampling strategy that generalize across view synthesis tasks at test time. As a result, our samples maintain high consistency without requiring additional 3D representation-based distillation, thus streamlining view synthesis in the wild. Furthermore, we show that our method can generate high-quality videos lasting up to half a minute with seamless loop closure. Extensive benchmarking demonstrates that Seva outperforms existing methods across different datasets and settings. Project page with code and model: https://stable-virtual-camera.github.io/.

Key facts. Cited by 179 papers in the map (data through 7 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 54 of its 69 references that are in the map. First posted on arXiv 18 Mar 2025.

Builds on

54 of 69 references.

Closest ancestors · 12

Same direction, newest first

  1. 2024You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale9 Dec
  2. 2024ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis3 Sep
  3. 2024Controlling Space and Time with Diffusion Models10 Jul
  4. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Models16 May
  5. 2024SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion18 Mar
  6. 2023ReconFusion: 3D Reconstruction with Diffusion Priors5 Dec
  7. 2023Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model23 Oct
  8. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Image7 Sep
  9. 2023MVDream: Multi-view Diffusion for 3D Generation31 Aug
  10. 2023Long-Term Photometric Consistent Novel View Synthesis with Diffusion Models21 Apr
  11. 2023Zero-1-to-3: Zero-shot One Image to 3D Object20 Mar
  12. 2022DreamFusion: Text-to-3D using 2D Diffusion29 Sep

Other references · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  6. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  7. 2022Classifier-Free Diffusion Guidancecited by 5,717
  8. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  9. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  10. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  11. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  12. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
30 more
  1. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,755
  2. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  3. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  4. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,479
  5. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,465
  6. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 834
  7. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 668
  8. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 667
  9. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 646
  10. 2024Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusioncited by 634
  11. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 601
  12. 2023MotionCtrl: A Unified and Flexible Motion Controller for Video Generationcited by 568
  13. 2024MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Imagescited by 553
  14. 2023DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Visioncited by 514
  15. 2022Latent-NeRF for Shape-Guided Generation of 3D Shapes and Texturescited by 506
  16. 2024CameraCtrl: Enabling Camera Control for Text-to-Video Generationcited by 448
  17. 2023Simple diffusion: End-to-end diffusion for high resolution imagescited by 413
  18. 2022Latent Video Diffusion Models for High-Fidelity Long Video Generationcited by 385
  19. 2023Splatter Image: Ultra-Fast Single-View 3D Reconstructioncited by 359
  20. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 324
  21. 2024DepthSplat: Connecting Gaussian Splatting and Depthcited by 275
  22. 20243D Gaussian Splatting as Markov Chain Monte Carlocited by 210
  23. 20234D-fy: Text-to-4D Generation Using Hybrid Score Distillation Samplingcited by 184
  24. 2024LVSM: A Large View Synthesis Model with Minimal 3D Inductive Biascited by 178
  25. 2024RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videoscited by 113
  26. 2024Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splatscited by 111
  27. 2021Light Field Neural Renderingcited by 108
  28. 2023Motion-Conditioned Diffusion Model for Controllable Video Synthesiscited by 99
  29. 2023Free3D: Consistent Novel View Synthesis without 3D Representationcited by 72
  30. 2024HexaGen3D: StableDiffusion is just one step away from Fast and Diverse Text-to-3D Generationcited by 21

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 68; 2026: 111.

179 papers.

Sort:

By area:

  1. 2025MapAnything: Universal Feed-Forward Metric 3D Reconstructioncited by 295
  2. 2025ViPE: Video Pose Engine for 3D Geometric Perceptioncited by 162
  3. 2025WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modelingcited by 152
  4. 2025VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memorycited by 102
  5. 2025Cameras as Relative Positional Encodingcited by 94
  6. 2025Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generationcited by 93
  7. 2025Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generationcited by 75
  8. 2026PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulationcited by 74
  9. 2025MotionStream: Real-Time Video Generation with Interactive Motion Controlscited by 71
  10. 2026SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformercited by 50
  11. 2025MindJourney: Test-Time Scaling with World Models for Spatial Reasoningcited by 49
  12. 2025CamCloneMaster: Enabling Reference-based Camera Control for Video Generationcited by 44
38 more
  1. 2025World-in-World: World Models in a Closed-Loop Worldcited by 44
  2. 2025Unified Camera Positional Encoding for Controlled Video Generationcited by 34
  3. 2026HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worldscited by 34
  4. 2025Spatia: Video Generation with Updatable Spatial Memorycited by 33
  5. 2025WorldExplorer: Towards Generating Fully Navigable 3D Scenescited by 26
  6. 2026Gen3R: 3D Scene Generation Meets Feed-Forward Reconstructioncited by 24
  7. 2025Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Surveycited by 23
  8. 2026MosaicMem: Hybrid Spatial Memory for Controllable Video World Modelscited by 23
  9. 2025Epipolar Geometry Improves Video Generation Modelscited by 22
  10. 2025Generative Video Motion Editing with 3D Point Trackscited by 21
  11. 2025EPiC: Efficient Video Camera Control Learning with Precise Anchor-Video Guidancecited by 20
  12. 2025Positional Encoding Fieldcited by 20
  13. 2026Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Modelscited by 20
  14. 2025Viser: Imperative, Web-based 3D Visualization in Pythoncited by 19
  15. 2025Sharp Monocular View Synthesis in Less Than a Secondcited by 19
  16. 2025TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Modelscited by 18
  17. 2025DreamNav: A Trajectory-Based Imaginative Framework for Zero-Shot Vision-and-Language Navigationcited by 15
  18. 2025Dexterous World Modelscited by 15
  19. 2026WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memoriescited by 15
  20. 2026Vista4D: Video Reshooting with 4D Point Cloudscited by 15
  21. 2026AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memoriescited by 13
  22. 2026When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoningcited by 12
  23. 2026Repurposing Geometric Foundation Models for Multi-view Diffusioncited by 12
  24. 2025DualCamCtrl: Dual-Branch Diffusion Model for Geometry-Aware Camera-Controlled Video Generationcited by 11
  25. 2025G4Splat: Geometry-Guided Gaussian Splatting with Generative Priorcited by 10
  26. 2025SpatialDreamer: Incentivizing Spatial Reasoning via Active Mental Imagerycited by 10
  27. 2026RayRoPE: Projective Ray Positional Encoding for Multi-view Attentioncited by 10
  28. 2026One2Scene: Geometric Consistent Explorable 3D Scene Generation from a Single Imagecited by 10
  29. 2026MemoBench: Benchmarking World Modeling in Dynamically Changing Environmentscited by 10
  30. 2025SpaceTimePilot: Generative Rendering of Dynamic Scenes Across Space and Timecited by 9
  31. 2026PerpetualWonder: Long-Horizon Action-Conditioned 4D Scene Generationcited by 9
  32. 2025VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Modelscited by 8
  33. 2025Scaling Sequence-to-Sequence Generative Neural Renderingcited by 8
  34. 2025CUPID: Generative 3D Reconstruction via Joint Object and Pose Modelingcited by 8
  35. 2025One4D: Unified 4D Generation and Reconstruction via Decoupled LoRA Controlcited by 8
  36. 2025CAMEO: Correspondence-Attention Alignment for Multi-View Diffusion Modelscited by 8
  37. 2026World Reconstruction From Inconsistent Viewscited by 8
  38. 2025IDCNet: Guided Video Diffusion for Metric-Consistent RGBD Scene Generation with Precise Camera Controlcited by 7

50 most cited of 179 All 179 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Consistent View Synthesis with Pose-Guided Diffusion Models
  2. 2024NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizer
  3. 2023ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models
  4. 2024Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis
  5. 2024Novel View Synthesis with Pixel-Space Diffusion Models
  6. 2024FSViewFusion: Few-Shots View Generation of Novel Objects
  7. 2025Geometric Consistency Refinement for Single Image Novel View Synthesis via Test-Time Adaptation of Diffusion Models
  8. 20243D-free meets 3D priors: Novel View Synthesis from a Single Image with Pretrained Diffusion Guidance